MétaCan
Menu
Back to cohort
Record W4414197327 · doi:10.1109/cvprw67362.2025.00056

Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models

2025· article· en· W4414197327 on OpenAlexaff
Jierun Chen, Fangyun Wei, Jinjing Zhao, Sizhe Song, Bohuai Wu, Zhuoxuan Peng, S.-H. Gary Chan, Hongyang Zhang

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicSpeech and dialogue systems
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsBenchmark (surveying)ComprehensionVocabularyObject (grammar)BenchmarkingKey (lock)

Abstract

fetched live from OpenAlex

Referring expression comprehension (REC) involves localizing a target instance based on a textual description. Recent advancements in REC have been driven by large multimodal models (LMMs) like CogVLM, which achieved 92.44% accuracy on RefCOCO. However, this study questions whether existing benchmarks such as RefCOCO, RefCOCO+, and RefCOCOg, capture LMMs' comprehensive capabilities. We begin with a manual examination of these benchmarks, revealing high labeling error rates: 14 % in RefCOCO, 24% in RefCOCO+, and 5% in RefCOCOg, which undermines the authenticity of evaluations. We address this by excluding problematic instances and reevaluating several LMMs capable of handling the REC task, showing significant accuracy improvements, thus highlighting the impact of benchmark noise. In response, we introduce Ref-L4, a comprehensive REC benchmark, specifically designed to evaluate modern REC models. Ref-L4 is distinguished by four key features: 1) a substantial sample size with 45,341 annotations; 2) a diverse range of object categories with 365 distinct types and varying instance sizes from 30 to 3,767; 3) lengthy referring expressions averaging 24.2 words; and 4) an extensive vocabulary comprising 22,813 unique words. We evaluate a total of 24 large models on Ref-L4 and provide valuable insights. The cleaned versions of RefCOCO, RefCOCO+, and RefCOCOg, as well as our Ref-L4 benchmark and evaluation code, are available at https://github.com/JierunChen/Ref-L4.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.018
metaresearch head score (Gemma)0.078
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.023
Threshold uncertainty score0.097

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0180.078
Meta-epidemiology (narrow)0.0040.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0030.003
Science and technology studies0.0020.002
Scholarly communication0.0060.010
Open science0.0060.006
Research integrity0.0040.006
Insufficient payload (model declined to judge)0.0100.008

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.046
GPT teacher head0.321
Teacher spread0.275 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations9
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicSpeech and dialogue systemsFrench-language works237,207